Kotoba‑Whisper‑Bilingual v1.0 delivers 6.3× faster distilled Whisper models for Japanese and English ASR plus bidirectional speech‑to‑text translation, built from OpenAI’s Whisper large‑v3 via knowledge distillation with cross‑entropy and KL‑divergence loss.
Description in other languages
Statistics
Statistics as of Nov 16, 2026
Hugging Face downloads (last 30 days)
4,000
Hugging Face likes
19
Listed
Oct 1, 2024
Downloads (30-day window) over time
Show as a table
| Month | DL (30d) |
|---|---|
| Dec 2025 | 2,000 |
| Jan 2026 | 9,000 |
| Feb 2026 | 10,000 |
| Mar 2026 | 8,000 |
| Apr 2026 | 7,000 |
| May 2026 | 10,000 |
| Jun 2026 | 8,000 |
| Jul 2026 | 7,000 |
| Aug 2026 | 13,000 |
| Sep 2026 | 7,000 |
| Oct 2026 | 4,000 |
| Nov 2026 | 4,000 |
Downloads over the 30 days before the last snapshot of each month.
Popular in the same category
- wav2vec2-large-xlsr-53-japanesejonatasgrosman16MJapanese wav2vec‑2 XLSR‑53 fine‑tuned on Common Voice 6.1, CSS10, and JSUT, requiring 16 kHz audio and usable via HuggingSound or HuggingFace pipelines.
- wav2vec2-large-xlsr-japanese-hiraganavumichien153kA Japanese speech‑recognition model fine‑tuned from facebook/wav2vec2‑large‑xlsr‑53 on Common Voice and the JSUT corpus, optimized for 16 kHz audio input.
- anime-whisperlitagin33kAnime Whisper is a lightweight Japanese ASR model fine‑tuned on ~5,300 h of anime‑style dialogue that delivers low hallucination, rhythm‑aligned punctuation and accurate transcription of non‑verbal sounds and NSFW content, and must be run without an initial prompt.
- kotoba-whisper-v2.0kotoba-tech25kKotoba‑Whisper v2.0 is a Japanese ASR model distilled from OpenAI Whisper large‑v3, trained on 7.2 million ReazonSpeech clips, that runs 6.3× faster while matching the teacher’s CER/WER on in‑domain tests and includes stable‑ts/punctuation support and full training code on GitHub.
- kotoba-whisper-v2.2kotoba-tech16kKotoba‑Whisper‑v2.2 is a Japanese ASR model extending kotoba‑whisper‑v2.0 with integrated diarization and automatic punctuation via a HuggingFace‑Transformers pipeline, built in collaboration with Asahi Ushio and Kotoba Technologies.
- Qwen3-ASR-1.7B-JAneosophie13kFine‑tuned Qwen3‑ASR‑1.7B for Japanese ASR, optimized to accurately transcribe proper nouns, organization and product names, kanji‑heavy and mixed Japanese/English technical terms.
Resources in similar research fields
asrzakuro-ai72Automatic Speech Recognition with deepspeech2 model in pytorch with support from Zakuro AI.GitHubShared: Speech Recognition・Text Generation- parakeet-tdt_ctc-0.6b-janvidia7kNVIDIA NeMo’s 0.6 B‑parameter Hybrid FastConformer‑TDT‑CTC ASR model transcribes Japanese speech with punctuation and is available for inference or fine‑tuning within the NeMo framework.Shared: Text Generation・Speech & Audio in NLP
- japanese-anime-speechjoujiboi946Japanese Anime Speech Dataset offers 73,004 audio‑text pairs (110 hours total, evolving from V1 to V5) to enhance ASR models such as OpenAI’s Whisper, available under an open license for all uses with credit appreciated.HF datasetShared: Speech Recognition・Text Generation
- kotoba-whisper-v2.0-fasterkotoba-tech13kKotoba Whisper v2.0 is converted to CTranslate2 format for use with CTranslate2 and faster‑whisper, providing installation, inference examples, Apple M2 benchmarking, and conversion instructions.Shared: Speech Recognition・Speech & Audio in NLP
- japanese-hubert-base-phoneme-ctc-v4prj-beatrice12kFine‑tuned Japanese Hubert‑Base for CTC phoneme recognition (v4) with updated sentence‑filtering rules, pronunciation adjustments, and a GPU switch to A6000, stopped training at 110k steps.Shared: Speech Recognition・Speech & Audio in NLP
- japanese-wav2vec2-base-rs35khreazon-research10kJapanese‑wav2vec2‑base‑rs35kh is a 96.7 M‑parameter wav2vec 2.0 Base model fine‑tuned on the ReazonSpeech v2.0 Japanese ASR corpus, reaching a 13.22 % CER, deployable with Hugging Face transformers, and released under an Apache 2.0 license.Shared: Speech Recognition・Speech & Audio in NLP